Life Expectancy Prediction using Linear Regression
In [2]:
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error
import plotly.express as px
from sklearn.model_selection import train_test_split
In [3]:
df=pd.read_csv('Life expectancy data.csv')
df.head()
Out[3]:
| Country | Year | Status | Life expectancy | Adult Mortality | infant deaths | Alcohol | percentage expenditure | Hepatitis B | Measles | ... | Polio | Total expenditure | Diphtheria | HIV/AIDS | GDP | Population | thinness 1-19 years | thinness 5-9 years | Income composition of resources | Schooling | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | Afghanistan | 2015 | Developing | 65.0 | 263.0 | 62 | 0.01 | 71.279624 | 65.0 | 1154 | ... | 6.0 | 8.16 | 65.0 | 0.1 | 584.259210 | 33736494.0 | 17.2 | 17.3 | 0.479 | 10.1 |
| 1 | Afghanistan | 2014 | Developing | 59.9 | 271.0 | 64 | 0.01 | 73.523582 | 62.0 | 492 | ... | 58.0 | 8.18 | 62.0 | 0.1 | 612.696514 | 327582.0 | 17.5 | 17.5 | 0.476 | 10.0 |
| 2 | Afghanistan | 2013 | Developing | 59.9 | 268.0 | 66 | 0.01 | 73.219243 | 64.0 | 430 | ... | 62.0 | 8.13 | 64.0 | 0.1 | 631.744976 | 31731688.0 | 17.7 | 17.7 | 0.470 | 9.9 |
| 3 | Afghanistan | 2012 | Developing | 59.5 | 272.0 | 69 | 0.01 | 78.184215 | 67.0 | 2787 | ... | 67.0 | 8.52 | 67.0 | 0.1 | 669.959000 | 3696958.0 | 17.9 | 18.0 | 0.463 | 9.8 |
| 4 | Afghanistan | 2011 | Developing | 59.2 | 275.0 | 71 | 0.01 | 7.097109 | 68.0 | 3013 | ... | 68.0 | 7.87 | 68.0 | 0.1 | 63.537231 | 2978599.0 | 18.2 | 18.2 | 0.454 | 9.5 |
5 rows × 22 columns
In [4]:
df.shape
Out[4]:
(2938, 22)
In [5]:
df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 2938 entries, 0 to 2937 Data columns (total 22 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Country 2938 non-null object 1 Year 2938 non-null int64 2 Status 2938 non-null object 3 Life expectancy 2928 non-null float64 4 Adult Mortality 2928 non-null float64 5 infant deaths 2938 non-null int64 6 Alcohol 2744 non-null float64 7 percentage expenditure 2938 non-null float64 8 Hepatitis B 2385 non-null float64 9 Measles 2938 non-null int64 10 BMI 2904 non-null float64 11 under-five deaths 2938 non-null int64 12 Polio 2919 non-null float64 13 Total expenditure 2712 non-null float64 14 Diphtheria 2919 non-null float64 15 HIV/AIDS 2938 non-null float64 16 GDP 2490 non-null float64 17 Population 2286 non-null float64 18 thinness 1-19 years 2904 non-null float64 19 thinness 5-9 years 2904 non-null float64 20 Income composition of resources 2771 non-null float64 21 Schooling 2775 non-null float64 dtypes: float64(16), int64(4), object(2) memory usage: 505.1+ KB
In [6]:
df.isnull().sum()
Out[6]:
Country 0 Year 0 Status 0 Life expectancy 10 Adult Mortality 10 infant deaths 0 Alcohol 194 percentage expenditure 0 Hepatitis B 553 Measles 0 BMI 34 under-five deaths 0 Polio 19 Total expenditure 226 Diphtheria 19 HIV/AIDS 0 GDP 448 Population 652 thinness 1-19 years 34 thinness 5-9 years 34 Income composition of resources 167 Schooling 163 dtype: int64
In [7]:
df.describe()
Out[7]:
| Year | Life expectancy | Adult Mortality | infant deaths | Alcohol | percentage expenditure | Hepatitis B | Measles | BMI | under-five deaths | Polio | Total expenditure | Diphtheria | HIV/AIDS | GDP | Population | thinness 1-19 years | thinness 5-9 years | Income composition of resources | Schooling | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 2938.000000 | 2928.000000 | 2928.000000 | 2938.000000 | 2744.000000 | 2938.000000 | 2385.000000 | 2938.000000 | 2904.000000 | 2938.000000 | 2919.000000 | 2712.00000 | 2919.000000 | 2938.000000 | 2490.000000 | 2.286000e+03 | 2904.000000 | 2904.000000 | 2771.000000 | 2775.000000 |
| mean | 2007.518720 | 69.224932 | 164.796448 | 30.303948 | 4.602861 | 738.251295 | 80.940461 | 2419.592240 | 38.321247 | 42.035739 | 82.550188 | 5.93819 | 82.324084 | 1.742103 | 7483.158469 | 1.275338e+07 | 4.839704 | 4.870317 | 0.627551 | 11.992793 |
| std | 4.613841 | 9.523867 | 124.292079 | 117.926501 | 4.052413 | 1987.914858 | 25.070016 | 11467.272489 | 20.044034 | 160.445548 | 23.428046 | 2.49832 | 23.716912 | 5.077785 | 14270.169342 | 6.101210e+07 | 4.420195 | 4.508882 | 0.210904 | 3.358920 |
| min | 2000.000000 | 36.300000 | 1.000000 | 0.000000 | 0.010000 | 0.000000 | 1.000000 | 0.000000 | 1.000000 | 0.000000 | 3.000000 | 0.37000 | 2.000000 | 0.100000 | 1.681350 | 3.400000e+01 | 0.100000 | 0.100000 | 0.000000 | 0.000000 |
| 25% | 2004.000000 | 63.100000 | 74.000000 | 0.000000 | 0.877500 | 4.685343 | 77.000000 | 0.000000 | 19.300000 | 0.000000 | 78.000000 | 4.26000 | 78.000000 | 0.100000 | 463.935626 | 1.957932e+05 | 1.600000 | 1.500000 | 0.493000 | 10.100000 |
| 50% | 2008.000000 | 72.100000 | 144.000000 | 3.000000 | 3.755000 | 64.912906 | 92.000000 | 17.000000 | 43.500000 | 4.000000 | 93.000000 | 5.75500 | 93.000000 | 0.100000 | 1766.947595 | 1.386542e+06 | 3.300000 | 3.300000 | 0.677000 | 12.300000 |
| 75% | 2012.000000 | 75.700000 | 228.000000 | 22.000000 | 7.702500 | 441.534144 | 97.000000 | 360.250000 | 56.200000 | 28.000000 | 97.000000 | 7.49250 | 97.000000 | 0.800000 | 5910.806335 | 7.420359e+06 | 7.200000 | 7.200000 | 0.779000 | 14.300000 |
| max | 2015.000000 | 89.000000 | 723.000000 | 1800.000000 | 17.870000 | 19479.911610 | 99.000000 | 212183.000000 | 87.300000 | 2500.000000 | 99.000000 | 17.60000 | 99.000000 | 50.600000 | 119172.741800 | 1.293859e+09 | 27.700000 | 28.600000 | 0.948000 | 20.700000 |
In [8]:
df.describe(include = object)
Out[8]:
| Country | Status | |
|---|---|---|
| count | 2938 | 2938 |
| unique | 193 | 2 |
| top | Afghanistan | Developing |
| freq | 16 | 2426 |
In [9]:
df.columns
Out[9]:
Index(['Country', 'Year', 'Status', 'Life expectancy ', 'Adult Mortality',
'infant deaths', 'Alcohol', 'percentage expenditure', 'Hepatitis B',
'Measles ', ' BMI ', 'under-five deaths ', 'Polio', 'Total expenditure',
'Diphtheria ', ' HIV/AIDS', 'GDP', 'Population',
' thinness 1-19 years', ' thinness 5-9 years',
'Income composition of resources', 'Schooling'],
dtype='object')
In [10]:
df.isnull().sum()
Out[10]:
Country 0 Year 0 Status 0 Life expectancy 10 Adult Mortality 10 infant deaths 0 Alcohol 194 percentage expenditure 0 Hepatitis B 553 Measles 0 BMI 34 under-five deaths 0 Polio 19 Total expenditure 226 Diphtheria 19 HIV/AIDS 0 GDP 448 Population 652 thinness 1-19 years 34 thinness 5-9 years 34 Income composition of resources 167 Schooling 163 dtype: int64
In [11]:
from sklearn.impute import SimpleImputer
imputer=SimpleImputer(missing_values=np.nan, strategy='mean', fill_value=None)
df['Life expectancy ']=imputer.fit_transform(df[['Life expectancy ']])
In [12]:
df.isnull().sum()
Out[12]:
Country 0 Year 0 Status 0 Life expectancy 0 Adult Mortality 10 infant deaths 0 Alcohol 194 percentage expenditure 0 Hepatitis B 553 Measles 0 BMI 34 under-five deaths 0 Polio 19 Total expenditure 226 Diphtheria 19 HIV/AIDS 0 GDP 448 Population 652 thinness 1-19 years 34 thinness 5-9 years 34 Income composition of resources 167 Schooling 163 dtype: int64
In [13]:
df['Adult Mortality']=imputer.fit_transform(df[['Adult Mortality']])
df['Alcohol']=imputer.fit_transform(df[['Alcohol']])
df['Hepatitis B']=imputer.fit_transform(df[['Hepatitis B']])
df[' BMI ']=imputer.fit_transform(df[[' BMI ']])
df['Polio']=imputer.fit_transform(df[['Polio']])
df['Total expenditure']=imputer.fit_transform(df[['Total expenditure']])
df['Diphtheria ']=imputer.fit_transform(df[['Diphtheria ']])
df['GDP']=imputer.fit_transform(df[['GDP']])
df['Population']=imputer.fit_transform(df[['Population']])
df[' thinness 1-19 years']=imputer.fit_transform(df[[' thinness 1-19 years']])
df[' thinness 5-9 years']=imputer.fit_transform(df[[' thinness 5-9 years']])
df['Schooling']=imputer.fit_transform(df[['Schooling']])
df['Income composition of resources']=imputer.fit_transform(df[['Income composition of resources']])
In [14]:
df.isnull().sum()
Out[14]:
Country 0 Year 0 Status 0 Life expectancy 0 Adult Mortality 0 infant deaths 0 Alcohol 0 percentage expenditure 0 Hepatitis B 0 Measles 0 BMI 0 under-five deaths 0 Polio 0 Total expenditure 0 Diphtheria 0 HIV/AIDS 0 GDP 0 Population 0 thinness 1-19 years 0 thinness 5-9 years 0 Income composition of resources 0 Schooling 0 dtype: int64
In [15]:
LR=LinearRegression()
In [16]:
#LR.fit('Status', 'life expectancy')
#Status=np.array(['Status']).reshape(-1,1)
#Life_expectancy=np.array(['Life expectancy'])
In [17]:
#life_expectancy=np.array(['Life expectancy']).reshape(-1,1)
#LR.fit(life_expectancy, Status)
In [18]:
target=df['Life expectancy ']
features=df[df.columns.difference(['Life expectancy ', 'Year'])]
In [19]:
x_train, x_test, y_train, y_test= train_test_split(pd.get_dummies(features), target, test_size=0.3)
In [20]:
LR.fit(x_train, y_train)
Out[20]:
LinearRegression()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
LinearRegression()
In [21]:
LR.confidence=LR.score(x_test, y_test)
In [22]:
print('Confidence: ',LR.confidence)
Confidence: 0.9487860011999055
In [23]:
y_pred= LR.predict(x_test)
In [24]:
y_pred
Out[24]:
array([81.85419968, 67.92341237, 63.016682 , 50.36671115, 69.96883514,
65.53567492, 56.30445063, 67.35053485, 75.09553312, 69.30914511,
73.41097751, 75.18563566, 75.02683601, 74.6361224 , 67.80414756,
68.67625386, 74.13642529, 64.93813022, 55.88557134, 74.579394 ,
76.47216953, 69.80990543, 80.75913176, 69.37032588, 69.51204204,
82.52777391, 65.38201439, 80.30732601, 76.77864358, 64.94018683,
56.08991717, 78.52788793, 75.91809007, 74.33704424, 49.81369249,
74.78614199, 72.81807758, 72.10426166, 74.13355367, 59.65229487,
61.58828443, 81.55922399, 80.49697381, 58.0797026 , 65.77691081,
78.35841205, 64.64583721, 58.44452776, 67.18145456, 45.7424849 ,
81.37422286, 65.45648501, 56.98734108, 72.18397753, 44.54714595,
63.09965117, 80.4701423 , 72.71065435, 81.8971594 , 65.11332245,
80.31023132, 75.67317245, 73.9141879 , 76.78226308, 67.75360851,
74.2518846 , 59.37104583, 70.04939339, 80.66506238, 60.28663969,
61.06909435, 65.55927562, 71.72723521, 74.08612318, 82.21611116,
81.67237996, 61.42536363, 75.38761468, 71.95253921, 81.27229826,
65.85361574, 48.48133983, 56.45144782, 82.91437736, 45.39432981,
47.09127591, 81.06100099, 68.52519408, 60.60609032, 73.75745595,
53.91606876, 68.69493527, 73.95984356, 77.44985671, 54.28442908,
66.62065872, 72.00078053, 76.65888394, 82.25505076, 77.1447203 ,
52.61370758, 72.96889479, 77.21067276, 66.78107706, 79.50533325,
56.23978691, 50.92940109, 73.31109466, 80.38333062, 73.81445277,
76.81280842, 57.69792237, 69.74510664, 81.5985041 , 75.30017726,
55.26352325, 46.74937256, 73.79181912, 75.05696551, 75.15693334,
56.79151061, 82.76049632, 73.63678612, 81.76138833, 77.55015621,
68.54102574, 79.92541759, 53.86760899, 75.31204515, 68.18377351,
75.91167288, 56.91231934, 60.88255646, 74.03693308, 49.0499561 ,
78.24317545, 68.84348473, 73.80662707, 81.89673489, 67.64431277,
83.7983134 , 82.19019848, 66.82150506, 77.41999727, 57.10088739,
57.35139543, 84.17805688, 71.89839534, 56.24871715, 83.28709155,
60.44750604, 68.69747954, 80.632294 , 61.55065843, 54.53958577,
73.36468225, 76.1361586 , 56.70264438, 82.72059229, 80.848434 ,
60.82869099, 61.65747887, 53.49176909, 71.56224208, 68.05910228,
76.39568686, 65.68860841, 69.55714579, 63.5019186 , 79.4298939 ,
59.79062215, 64.87920472, 81.37124428, 81.77660038, 75.04907039,
73.11809899, 64.50670083, 56.99779022, 74.82963878, 63.55181108,
46.76522472, 79.94204306, 50.5461329 , 44.26761581, 67.83256361,
72.29611315, 56.77999634, 68.46089021, 72.99933795, 74.66880817,
64.19149049, 77.47280149, 78.16236842, 69.04631017, 68.49468137,
82.02060136, 75.77160462, 76.18776684, 62.61430271, 65.55530529,
61.4647328 , 72.10317149, 64.54384876, 53.7933153 , 74.05584908,
73.77288514, 71.73329919, 56.13331662, 78.88859613, 42.28626892,
76.26732817, 72.08136755, 73.18835686, 73.34008711, 73.31794355,
69.65998289, 73.20576687, 69.24099083, 75.90463176, 59.07647481,
81.86811685, 60.79873231, 61.21836873, 57.74974711, 75.02670276,
82.27708243, 62.56292404, 57.4658889 , 74.11340186, 76.55753402,
75.74177489, 74.52652377, 58.86693326, 65.60065365, 50.98757388,
66.49127171, 75.51179387, 82.74375373, 71.99930819, 63.61686135,
72.29107314, 82.41388756, 65.98656005, 81.25166877, 57.70111446,
54.42440247, 67.96249626, 76.02166144, 63.6435276 , 77.7457721 ,
50.56686819, 81.89038303, 56.90599822, 64.92612522, 72.93627543,
63.33398641, 70.77730424, 72.75033533, 61.19622281, 81.28620337,
78.96648772, 53.19982346, 55.27224783, 59.61576188, 69.08285996,
62.81141687, 72.95477182, 72.15662777, 59.1269013 , 80.571666 ,
79.66397571, 73.50674832, 68.24233969, 64.1328705 , 71.42653566,
56.59690272, 73.1801266 , 52.4279138 , 70.69396063, 57.06868377,
54.44730592, 58.41663702, 58.99580022, 79.33405405, 59.37791557,
71.82146518, 56.23347431, 55.36568175, 73.13040001, 65.72948735,
73.81727319, 65.52358885, 74.2396838 , 68.54724213, 64.65763836,
80.56353593, 60.5643533 , 56.62984208, 72.86257107, 50.65069056,
80.59650249, 82.74183119, 62.69437795, 68.54136163, 70.89187549,
69.32182096, 72.25577713, 76.09186129, 69.33490045, 62.53154411,
53.97574879, 52.68253978, 74.70238027, 58.99516341, 82.97092528,
74.25921616, 54.52236889, 70.07881516, 83.30668737, 78.1701195 ,
79.70345987, 55.96900471, 76.01236999, 81.35654551, 80.16150076,
54.20135578, 50.03408356, 82.3300927 , 67.33957642, 73.90098989,
71.38929046, 71.54063148, 76.65238957, 56.62564317, 82.02844175,
62.9727764 , 54.11781478, 71.73116892, 82.64685695, 48.75450322,
77.56542482, 83.10590218, 74.1226752 , 72.80030571, 55.71903353,
79.60809297, 61.15900153, 72.67962465, 76.02538333, 73.88445881,
83.08977062, 58.72228865, 73.79290753, 53.77000928, 68.39909436,
75.28850758, 73.9892441 , 72.78290765, 52.73899705, 73.94521129,
54.00082712, 81.27547271, 68.48858643, 71.11083954, 47.51847232,
70.62430715, 72.91764631, 47.36027629, 70.0804118 , 64.99719561,
58.75310041, 52.37532774, 70.39132274, 50.08004159, 73.1032761 ,
78.1530071 , 55.86517055, 75.82868037, 83.53049964, 74.03234809,
69.73964722, 70.94479547, 63.46890725, 51.89510925, 57.50154572,
76.74110733, 81.54815829, 61.56021624, 68.04493027, 72.81973507,
82.3165796 , 70.16614309, 67.9048524 , 64.30630549, 59.03572668,
74.18350818, 71.51860355, 72.49267337, 73.61708695, 75.06986261,
64.76207864, 73.79979301, 68.06157431, 56.52972823, 71.01172614,
68.28643967, 74.23324707, 73.62644988, 64.83159229, 72.18546614,
74.68870166, 62.5035707 , 75.2039345 , 72.34573016, 63.26299077,
76.85523659, 64.9394638 , 73.1793442 , 62.92390484, 74.8045401 ,
72.50767447, 58.46830423, 73.77794639, 75.62237313, 64.74667836,
72.32720679, 73.75806663, 81.88488532, 73.78329638, 67.86011543,
75.56389376, 74.56336801, 75.3731793 , 52.08344802, 73.61806669,
62.75775846, 65.07520601, 73.31279105, 74.23926718, 50.10138437,
62.22432424, 59.97215992, 49.59662849, 74.69745495, 73.83779736,
75.99158431, 49.20832766, 70.9379247 , 73.04337219, 73.93514917,
58.34396419, 75.99162499, 62.10871428, 65.52536772, 69.27315407,
57.06393342, 73.79169748, 72.97319159, 81.95228006, 68.24296889,
74.41026806, 80.46501607, 55.70291911, 79.39697817, 76.98110408,
44.20746743, 64.48000891, 76.87586095, 58.99603852, 78.84411849,
76.13803344, 75.10840248, 79.46687779, 63.40237107, 68.66088117,
48.15297671, 74.15668307, 68.08364448, 73.48844601, 73.17807973,
71.96587174, 71.55529544, 79.74994359, 56.47359485, 80.95693201,
61.56292599, 72.25613778, 74.58337371, 64.48132545, 79.75538908,
65.22412617, 69.23665804, 70.36491862, 68.70087457, 47.48339946,
73.98543737, 75.39566405, 68.77795654, 56.29972251, 73.15780146,
73.90030349, 65.71638898, 69.95892969, 80.52990076, 81.70973071,
79.41215385, 64.01974133, 72.11468777, 82.72499 , 79.57302263,
81.55955701, 60.56483741, 73.09228437, 69.81980483, 51.02737001,
74.72378131, 62.52568566, 55.24174932, 58.20879511, 69.83742298,
59.16966866, 75.94060864, 75.14754758, 62.96811216, 53.09790919,
60.01328517, 56.24318241, 70.30795708, 75.25340316, 59.27652578,
71.97178922, 57.06709409, 75.0481521 , 73.68643089, 70.10462424,
56.35590004, 61.21045595, 72.99501193, 62.65613 , 55.64648397,
81.03935948, 63.75287712, 70.08877802, 81.40897513, 74.61612175,
73.22666547, 59.84775414, 74.03443585, 75.15499619, 59.57253862,
55.18355814, 66.20254003, 62.07858684, 71.89150338, 72.85115103,
80.72842808, 81.40022168, 75.43501936, 74.65728966, 54.79664538,
75.11573865, 57.54183567, 70.60208447, 72.96918835, 64.7632742 ,
75.28870033, 45.17601139, 73.23428341, 67.46114876, 80.24279611,
72.93833673, 72.48731548, 79.22419628, 51.07781447, 58.77188772,
61.28020751, 73.60224019, 66.62140416, 64.37096615, 78.8764211 ,
63.27741778, 50.3306288 , 68.86160599, 69.20095966, 81.74873594,
56.83054866, 66.4522241 , 63.55770765, 80.04124671, 77.3889089 ,
49.127913 , 57.66403556, 75.63311503, 80.59971029, 74.41133254,
83.20536732, 80.81122263, 76.4946158 , 65.45664665, 76.67322931,
75.58998509, 54.18122289, 75.51111052, 74.13768523, 66.56802527,
67.58000295, 66.75781485, 65.06403412, 80.47308509, 80.45306075,
66.02707757, 68.05304203, 66.34534869, 83.13292859, 81.37487215,
73.59221864, 78.01400827, 54.86004101, 74.11260975, 54.26461958,
81.65727877, 79.52717668, 46.51044907, 76.58697523, 72.97877356,
63.03789558, 53.23667888, 65.61179822, 73.47784727, 78.47163422,
71.44334394, 72.76797398, 74.13175961, 81.3875667 , 72.6093583 ,
61.03924157, 64.40310215, 49.1104199 , 82.29365229, 72.3919204 ,
79.7033055 , 56.96312346, 76.23402707, 73.8669064 , 62.98469596,
68.96169393, 74.04340451, 63.18938276, 61.58914377, 76.66825828,
74.92667482, 73.26621163, 73.37029592, 73.67087293, 59.30538499,
72.64205173, 76.22281256, 65.78585898, 73.80415515, 64.02493902,
75.90528103, 65.64453941, 61.2160441 , 78.38687018, 76.6663046 ,
68.1588133 , 76.17947329, 74.93739343, 73.5853881 , 51.82967004,
76.0660838 , 71.72248006, 78.08204348, 58.72268104, 80.93702233,
74.40321311, 81.13082867, 53.5915655 , 69.50039915, 52.25910719,
58.84955868, 76.37629198, 73.26346266, 80.18805734, 73.21716033,
53.48706328, 71.81404744, 61.84631723, 74.136736 , 72.93888676,
52.45770421, 62.41304388, 71.07944639, 80.64539763, 82.05616553,
73.4876298 , 72.76980558, 61.10755305, 53.23906084, 76.51125538,
58.9585047 , 52.60530515, 61.10486981, 60.9527611 , 66.50220605,
63.93823543, 75.29464295, 71.57244778, 68.88964249, 75.85045002,
75.74124003, 55.46531964, 65.84106581, 68.28797221, 69.11719687,
78.46007073, 81.6858121 , 70.44150394, 73.45838105, 55.76230684,
48.65907507, 79.12389471, 74.19600681, 44.80376631, 41.95132313,
81.59498737, 63.08061101, 81.70325632, 75.09573602, 79.42744504,
72.41582504, 74.73365143, 74.24475209, 74.06029129, 51.16995367,
79.14384828, 60.49898598, 73.25840028, 72.12413577, 75.46018367,
72.48826586, 67.68117411, 69.70191414, 66.2370562 , 75.33878351,
83.44379341, 82.22482017, 74.07588135, 49.6712839 , 63.35149717,
68.21904595, 74.0159575 , 76.84812951, 66.38891911, 66.05796689,
63.40062326, 55.10705454, 74.39657889, 70.12174767, 71.17193587,
81.15037472, 72.93822001, 69.02866829, 57.54971249, 74.89578371,
64.8469979 , 75.7586391 , 73.95431545, 71.89081959, 72.58413694,
66.32027679, 68.67937323, 76.13660726, 71.94943166, 67.9564615 ,
58.81121777, 58.43994387, 53.39764988, 81.89882897, 63.72323483,
62.0339733 , 70.38056752, 62.9967007 , 73.14852833, 80.01262557,
68.20959753, 74.97994052, 81.4076586 , 72.40918526, 54.29415232,
68.01395055, 65.6184783 , 65.99242096, 82.65248583, 74.13302565,
74.39672344, 73.34270754, 58.01172656, 62.59134463, 72.79020707,
53.02829256, 82.10148407, 71.86542853, 72.84521625, 66.34476962,
79.83108419, 73.902185 , 72.86035875, 74.9147477 , 82.63948259,
64.36698264, 74.6456966 , 55.34093227, 81.92226502, 72.41771032,
81.0969912 , 73.90426284, 74.32428032, 45.30237513, 65.5250354 ,
72.20141846, 74.69143543, 73.57329408, 72.07738396, 73.51893182,
77.12002212, 73.38629978, 74.91868581, 58.32021119, 69.84402571,
53.04280895, 74.18902946, 75.23406832, 72.18702893, 58.24787026,
78.17428717, 64.08016645, 77.56839848, 83.83823577, 75.71992736,
60.93267154, 82.21474172, 73.36150672, 73.82804986, 82.45945119,
73.87680044, 49.86864186, 60.3976354 , 69.32630821, 56.15812846,
66.18100598, 50.44709395, 70.10544623, 74.4926474 , 80.51459112,
72.22151917, 62.52987479, 71.05827794, 73.99941886, 58.95219672,
71.35020772, 73.50818654, 57.2119284 , 82.24554347, 66.52433227,
68.92024895, 69.76766776, 80.15425615, 58.29692786, 80.4052314 ,
55.94296893, 74.93504 , 74.25073525, 59.29438411, 69.27737618,
74.35034726, 56.35579992, 72.92373154, 61.23480985, 72.36966158,
74.07871046, 73.88789523])
In [25]:
plt.scatter(y_test, y_pred)
Out[25]:
<matplotlib.collections.PathCollection at 0x1e5a9a4be00>
In [26]:
plt.plot(y_test, y_pred)
Out[26]:
[<matplotlib.lines.Line2D at 0x1e5a5e0e3f0>]
In [27]:
mean_abs_err=mean_absolute_error(y_test, y_pred)
print('Mean absolute error: ',mean_abs_err)
Mean absolute error: 1.4058633740699258
In [28]:
mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mse)
rmae = np.sqrt(mae)
print("Mean Absolute Error (MAE):", mae)
print("Mean Squared Error (MSE):", mse)
print("Root Mean Squared Error (RMSE):", rmse)
print("Root Mean ABSOLUTE Error (RMSE):", rmae)
Mean Absolute Error (MAE): 1.4058633740699258 Mean Squared Error (MSE): 4.523359023056919 Root Mean Squared Error (RMSE): 2.126818991606225 Root Mean ABSOLUTE Error (RMSE): 1.1856910955514197
In [29]:
fig = px.pie(df, names='Status')
fig
In [74]:
df.columns
Out[74]:
Index(['Country', 'Year', 'Status', 'Life expectancy ', 'Adult Mortality',
'infant deaths', 'Alcohol', 'percentage expenditure', 'Hepatitis B',
'Measles ', ' BMI ', 'under-five deaths ', 'Polio', 'Total expenditure',
'Diphtheria ', ' HIV/AIDS', 'GDP', 'Population',
' thinness 1-19 years', ' thinness 5-9 years',
'Income composition of resources', 'Schooling'],
dtype='object')
In [78]:
plt.figure(figsize=(8,8))
sns.scatterplot(x=df['Adult Mortality'], y=df['Life expectancy '], hue=df['Alcohol'])
Out[78]:
<Axes: xlabel='Adult Mortality', ylabel='Life expectancy '>